Connectto Salesforce, Supabase, Firecrawl Deep Research MCP Servers

Create powerful AI workflows by connecting multiple MCP servers including Salesforce, Supabase, Firecrawl Deep Research for enhanced automation capabilities in Klavis AI.

Salesforce icon

Salesforce

featured

Salesforce is the world's leading customer relationship management (CRM) platform that helps businesses connect with customers, partners, and potential customers

Available Tools:

  • salesforce_query
  • salesforce_tooling_query
  • salesforce_describe_object
  • +2 more tools
Supabase icon

Supabase

featured

Supabase official MCP Server

Available Tools:

  • supabase_list_projects
  • supabase_get_project
  • supabase_get_cost
  • +21 more tools
Firecrawl Deep Research icon

Firecrawl Deep Research

featured

A personal research assistant that analyze sources across the web, based on Firecrawl

Available Tools:

  • firecrawl_deep_research

Quick Setup Guide

Follow these steps to connect LlamaIndex to these MCP servers

1

Create Your Account

Sign up for KlavisAI to access our MCP server management platform.

2

Configure Connections

Add your desired MCP servers to LlamaIndex and configure authentication settings.

3

Test & Deploy

Verify your connections work correctly and start using your enhanced AI capabilities.

LlamaIndex + KlavisAI Integration Snippets

import os
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType
from llama_index.tools.mcp import (
    BasicMCPClient,
    get_tools_from_mcp_url,
    aget_tools_from_mcp_url,
)
from llama_index.core.agent.workflow import FunctionAgent, AgentWorkflow

# Initialize clients
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))

salesforce_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.SALESFORCE,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

supabase_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.SUPABASE,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

firecrawl_deep_research_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.FIRECRAWL_DEEP_RESEARCH,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)
salesforce_tools = await aget_tools_from_mcp_url(
    salesforce_mcp_instance.server_url, 
    client=BasicMCPClient(salesforce_mcp_instance.server_url)
)
supabase_tools = await aget_tools_from_mcp_url(
    supabase_mcp_instance.server_url, 
    client=BasicMCPClient(supabase_mcp_instance.server_url)
)
firecrawl_deep_research_tools = await aget_tools_from_mcp_url(
    firecrawl_deep_research_mcp_instance.server_url, 
    client=BasicMCPClient(firecrawl_deep_research_mcp_instance.server_url)
)

salesforce_agent = FunctionAgent(
    name="salesforce_agent",
    tools=salesforce_tools,
    llm=llm,
)

supabase_agent = FunctionAgent(
    name="supabase_agent",
    tools=supabase_tools,
    llm=llm,
)

firecrawl_deep_research_agent = FunctionAgent(
    name="firecrawl_deep_research_agent",
    tools=firecrawl_deep_research_tools,
    llm=llm,
)
workflow = AgentWorkflow(
    agents=[salesforce_agent, supabase_agent, firecrawl_deep_research_agent],
    root_agent="salesforce_agent",
)

Frequently Asked Questions

Everything you need to know about connecting to these MCP servers

Ready to Get Started?

Join developers who are already using KlavisAI to power their LlamaIndex applications with these MCP servers.

Start For Free